Chronicles-OCR - Mature Script Classification: leaderboard
Chronicles-OCR (2026) tests vision-language models on historical Chinese writing across the Seven Chinese Scripts, 2,800 expert-annotated images from Oracle Bone to Cursive. This board scores naming which of the seven scripts a Clerical, Regular, Running or Cursive image shows, as accuracy in percent averaged over the four scripts; higher is better.
Metric: Accuracy (%) of classifying the image into one of the Seven Chinese Scripts, on images of the mature scripts (Clerical, Regular, Running and Cursive), the paper Average column over the per-script results; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 26 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Kimi K2.5 | Non-reasoning | 77 | #266 |
| 2 | Seed 2.0 Pro | Non-reasoning | 76.1 | #222 |
| 3 | Gemini 3.1 Pro (Preview) | 73.1 | #99 | |
| 4 | Qwen 3.5 397B A17B | Non-reasoning | 72.2 | #264 |
| 5 | Seed 1.8 | 71.1 | #252 | |
| 6 | Qwen 3.5 35B A3B | Non-reasoning | 68.1 | #492 |
| 7 | Claude Opus 4.7 | Thinking | 66.8 | #85 |
| 8 | Qwen 3 VL 235B A22B Instruct | 64.9 | #532 | |
| 9 | MiMo-V2-Omni | 62.3 | #465 | |
| 10 | GPT-5 | 62.1 | #178 | |
| 11 | Qwen 3 VL 8B Instruct | 60.9 | #1029 | |
| 12 | Qwen 3 VL 235B A22B (Thinking) | 60.4 | #459 | |
| 13 | InternVL3.5-241B-A28B | 58.1 | #733 | |
| 14 | Qwen 2.5 VL 72B Instruct | 57.2 | #841 | |
| 15 | Gemma 4 31B (IT) | 57.1 | #350 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=chronicles-ocr-mature-script-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.